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

    Neuronpedia

    INDEX
    Explanations

    instances where a statement is supported by additional information or examples

    oai_token-act-pair · gpt-3.5-turbo

    the word "also" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agus
    -0.78
    jam
    -0.69
    Stack
    -0.67
    acious
    -0.67
    ysis
    -0.66
     Ange
    -0.66
    ASE
    -0.66
     Essence
    -0.64
     Hearth
    -0.64
    cipled
    -0.64
    POSITIVE LOGITS
     includes
    0.83
     includ
    0.81
     included
    0.77
     contributed
    0.76
     known
    0.74
     anecd
    0.73
    vern
    0.73
     occasionally
    0.72
     include
    0.72
     referred
    0.72
    Act Density 0.128%

    No Known Activations