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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to qualities or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    descriptive adjectives relating to extreme characteristics and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abet
    -0.81
    adelphia
    -0.79
    weeney
    -0.77
    ©¶æ
    -0.77
    rera
    -0.76
    otin
    -0.74
    ioch
    -0.73
    ortium
    -0.73
    anamo
    -0.72
    ollo
    -0.71
    POSITIVE LOGITS
     alike
    1.60
     respectively
    0.95
     friendships
    0.73
     truths
    0.70
    entimes
    0.70
     views
    0.65
     perspectives
    0.65
     thereafter
    0.65
     striped
    0.64
     performances
    0.64
    Act Density 0.312%

    No Known Activations