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

    Neuronpedia

    INDEX
    Explanations

    verbs related to creation or improvement

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

    Followed by possessive pronouns (my, your) or "it"

    np_acts-logits-general · gemini-2.0-flash

    make things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    KommentareTeilen
    -0.58
    IsPostBack
    -0.55
    Démographie
    -0.53
     bezeichneter
    -0.51
    onAttach
    -0.50
     fournisseurs
    -0.50
    rrggbb
    -0.49
     śnie
    -0.48
    writeFieldEnd
    -0.48
    LayoutConstraint
    -0.47
    POSITIVE LOGITS
     sure
    1.08
     things
    0.83
     life
    0.81
     them
    0.80
     it
    0.79
     navigating
    0.71
     everything
    0.68
    sure
    0.65
    impossible
    0.63
    ficult
    0.63
    Act Density 0.112%

    No Known Activations