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

    Neuronpedia

    INDEX
    Explanations

    phrases related to movement or transportation from one place to another

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating movement or transfer between locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    QUI
    -0.78
    Extra
    -0.76
    Enlarge
    -0.71
    faced
    -0.70
    lied
    -0.70
    TEXT
    -0.69
    guards
    -0.68
    natureconservancy
    -0.68
     inval
    -0.66
    rite
    -0.65
    POSITIVE LOGITS
     whence
    1.00
     afar
    0.99
     thence
    0.96
     conception
    0.83
     inception
    0.81
     obscurity
    0.79
     point
    0.78
     Kuala
    0.73
     viewpoint
    0.72
     vantage
    0.69
    Act Density 0.102%

    No Known Activations