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

    Neuronpedia

    INDEX
    Explanations

    words or phrases related to directional movement

    oai_token-act-pair · gpt-3.5-turbo

    directional words related to movement or place

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gdala
    -0.86
    rast
    -0.78
    anan
    -0.78
    acea
    -0.75
    ocular
    -0.75
    mingham
    -0.74
    INS
    -0.73
    colo
    -0.71
    azo
    -0.71
    tein
    -0.69
    POSITIVE LOGITS
    robe
    0.97
    ly
    0.88
    ward
    0.86
     Bound
    0.81
    ness
    0.80
    wards
    0.79
     Compatibility
    0.78
    bound
    0.74
    Bound
    0.73
    nesses
    0.72
    Act Density 0.026%

    No Known Activations