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

    Neuronpedia

    INDEX
    Explanations

    statements expressing beliefs or opinions

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

    verbs expressing opinion, belief, or mental states (think, thought, hope, feel, say, contend, cautioned, assumed).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
    Eksterne
    -0.38
    Tembelea
    -0.36
    何も
    -0.34
    UnusedPrivate
    -0.33
    seguida
    -0.33
    PRNewswire
    -0.32
    Diwedd
    -0.31
    phosa
    -0.31
    balleur
    -0.30
    VolleyError
    -0.30
    POSITIVE LOGITS
     happens
    0.68
    happens
    0.63
     occurs
    0.61
     is
    0.58
     Happens
    0.55
     belongs
    0.54
     constitutes
    0.53
    occurs
    0.51
     isInitialized
    0.49
     corresponds
    0.49
    Act Density 0.183%

    No Known Activations