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

    Neuronpedia

    INDEX
    Explanations

    phrases related to a progress of time or degree

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating ongoing situations or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rium
    -0.70
    vec
    -0.66
     murd
    -0.63
    SourceFile
    -0.60
    illian
    -0.59
    Morning
    -0.58
     Killing
    -0.58
    }}}
    -0.57
    llular
    -0.57
    vation
    -0.57
    POSITIVE LOGITS
     unsuccessful
    0.90
     hasn
    0.79
     unsuccessfully
    0.77
     haven
    0.75
    successful
    0.75
     satisfactory
    0.69
     nobody
    0.69
     indications
    0.65
     there
    0.64
     we
    0.64
    Act Density 0.039%

    No Known Activations