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

    Neuronpedia

    INDEX
    Explanations

    directional terms such as north, east, west, and specific movements like migration

    oai_token-act-pair · gpt-3.5-turbo

    directional terms related to navigation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roma
    -0.63
    teness
    -0.61
    Ranked
    -0.61
    catentry
    -0.61
    TED
    -0.60
     nutshell
    -0.60
    Thumbnail
    -0.59
    DN
    -0.58
    byter
    -0.58
    "},"
    -0.57
    POSITIVE LOGITS
    wards
    1.59
    ward
    1.44
     toward
    1.23
     towards
    1.19
     into
    1.09
     onto
    0.98
    WARD
    0.96
    into
    0.92
    bound
    0.89
     through
    0.86
    Act Density 0.136%

    No Known Activations