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

    Neuronpedia

    INDEX
    Explanations

    conditional statements indicating a specific requirement for an action to take place

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements or phrases indicating specific requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hill
    -0.81
    thal
    -0.74
    Poké
    -0.73
    lez
    -0.73
    jab
    -0.71
    ãĥ´
    -0.68
    late
    -0.68
    ãĥīãĥ©
    -0.65
    ãĤ§
    -0.65
    anni
    -0.62
    POSITIVE LOGITS
     accompanied
    0.93
    ornia
    0.84
     they
    0.84
    soever
    0.80
    rame
    0.75
     someone
    0.74
     applied
    0.72
     somebody
    0.67
     preceded
    0.67
     confronted
    0.66
    Act Density 0.130%

    No Known Activations