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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to" indicating intentions or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ombs
    -0.17
    ijd
    -0.14
    hor
    -0.14
    gain
    -0.13
    برÛĮ
    -0.13
    ongo
    -0.13
    esin
    -0.13
    _SECURITY
    -0.13
    ije
    -0.13
    ivan
    -0.13
    POSITIVE LOGITS
     balance
    0.19
    artz
    0.15
    antz
    0.15
    çĿ
    0.15
     Balance
    0.14
     Hammer
    0.14
    uggle
    0.14
    ;
    0.14
    (
    0.14
    som
    0.14
    Act Density 0.036%

    No Known Activations