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

    Neuronpedia

    INDEX
    Explanations

    the word "stay" or its variations in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "stay" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NetMessage
    -0.82
    Ñı
    -0.77
    oros
    -0.71
     Cosponsors
    -0.70
    raid
    -0.70
    ologies
    -0.69
    DIT
    -0.69
    kson
    -0.68
    ortium
    -0.66
     Parables
    -0.65
    POSITIVE LOGITS
     afloat
    0.98
     silent
    0.81
    cation
    0.81
    overs
    0.79
     vigil
    0.77
     awake
    0.76
     undefeated
    0.76
     alive
    0.75
     quiet
    0.74
     awhile
    0.74
    Act Density 0.022%

    No Known Activations