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

    Neuronpedia

    INDEX
    Explanations

    words associated with events, characters, or specific names in a story or narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     DRAG
    -0.97
    ãĥ³
    -0.83
     ze
    -0.74
     Haku
    -0.72
    DOWN
    -0.71
    136
    -0.70
     radiation
    -0.70
     darts
    -0.69
     cerebral
    -0.69
     Brain
    -0.68
    POSITIVE LOGITS
    iv
    1.24
    ival
    1.23
    iva
    1.01
    IV
    1.00
    ivist
    0.96
    ott
    0.96
    ournals
    0.94
    ivalry
    0.94
    atti
    0.93
    iki
    0.92
    Act Density 0.110%

    No Known Activations