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

    Neuronpedia

    INDEX
    Explanations

    locations or places

    oai_token-act-pair · gpt-3.5-turbo

    topics related to transitions and changes across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    owship
    -0.67
    AFP
    -0.64
    rored
    -0.60
    »Ĵ
    -0.58
    ICAN
    -0.56
    ACTION
    -0.56
    ANK
    -0.55
    \.
    -0.54
    blance
    -0.54
    ibliography
    -0.54
    POSITIVE LOGITS
     onwards
    1.23
     onward
    1.14
     to
    1.01
     standpoint
    0.92
     beginnings
    0.90
    to
    0.82
     perspective
    0.77
     To
    0.76
     inception
    0.74
     downwards
    0.72
    Act Density 0.428%

    No Known Activations