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

    Neuronpedia

    INDEX
    Explanations

    verbs referring to actions or behaviors

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the necessity or conditions for reforms and changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     targ
    -0.60
    culosis
    -0.58
     Highlander
    -0.58
     onwards
    -0.55
     heats
    -0.55
     Supports
    -0.54
    ,[
    -0.54
     Luffy
    -0.54
     Poc
    -0.54
     Gravity
    -0.54
    POSITIVE LOGITS
    ĸļ
    0.72
    ateral
    0.71
    ŃĶ
    0.67
    ONSORED
    0.66
    ģĸ
    0.66
    STATE
    0.60
    avis
    0.60
    ually
    0.60
    depending
    0.59
    xit
    0.59
    Act Density 0.520%

    No Known Activations