Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    questions and phrases about experiences and observations that seek to understand or clarify situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Preceding words of "like," "be," or "is"

    np_acts-logits-general · gemini-2.0-flash

    what ... looks like

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chi̍t
    -0.55
    VolleyError
    -0.53
    ficulties
    -0.51
    stdc
    -0.49
    лару
    -0.49
     vectorielle
    -0.49
     doute
    -0.49
     demas
    -0.47
     olev
    -0.47
    bulin
    -0.46
    POSITIVE LOGITS
     looks
    0.93
     aussehen
    0.88
     look
    0.86
     wygląda
    0.83
     like
    0.82
     trông
    0.81
     вигля
    0.80
     Looks
    0.78
     aussieht
    0.76
     ressemb
    0.76
    Act Density 0.137%

    No Known Activations