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

    Neuronpedia

    INDEX
    Explanations

    phrases related to justifying a particular action or decision

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate justification or rationale

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mor
    -0.64
    Jar
    -0.61
    Dro
    -0.60
     las
    -0.57
     mascara
    -0.55
     Hunts
    -0.55
    thin
    -0.55
     tolerated
    -0.55
    cause
    -0.55
     choir
    -0.55
    POSITIVE LOGITS
    SPONSORED
    0.92
    >>>>>>>>
    0.70
    nings
    0.70
    isphere
    0.69
    asion
    0.68
    achy
    0.68
    irth
    0.68
    akedown
    0.67
    gha
    0.66
    ativity
    0.65
    Act Density 0.112%

    No Known Activations