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

    Neuronpedia

    INDEX
    Explanations

    phrases related to situations or qualities that are extremely difficult to overcome

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a state of being or capability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otaur
    -0.93
    udeb
    -0.91
    ËĪ
    -0.83
    arte
    -0.80
    raviolet
    -0.79
    oresc
    -0.76
    aeper
    -0.76
    ebus
    -0.75
    avers
    -0.75
    aphael
    -0.75
    POSITIVE LOGITS
    âĶĢâĶĢ
    0.91
     Haram
    0.80
    ties
    0.79
    itable
    0.76
    lihood
    0.75
     Danger
    0.74
    itarian
    0.73
    nesses
    0.71
    BILITY
    0.69
     charism
    0.68
    Act Density 0.022%

    No Known Activations