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

    Neuronpedia

    INDEX
    Explanations

    the word 'signaling' or variations thereof

    oai_token-act-pair · gpt-4-turbo

    words related to communication or intention

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to signaling or communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sm
    -0.80
    page
    -0.76
    zip
    -0.74
    awar
    -0.70
    pages
    -0.69
    iler
    -0.68
    ulk
    -0.66
    enne
    -0.65
    iar
    -0.64
    peg
    -0.64
    POSITIVE LOGITS
     signaling
    1.30
     signalling
    1.12
     signaled
    1.01
     signals
    0.98
     indicating
    0.87
     signal
    0.84
     signs
    0.84
     Signs
    0.83
     indications
    0.83
    ModLoader
    0.81
    Act Density 0.009%

    No Known Activations