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

    Neuronpedia

    INDEX
    Explanations

    words related to contact, primarily focused on physical touch or communication

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    corn
    -0.77
    umber
    -0.72
    ¦
    -0.71
    zees
    -0.67
    ffe
    -0.65
    Ħ¢
    -0.65
    perm
    -0.64
    cott
    -0.64
    ARR
    -0.64
    Rand
    -0.63
    POSITIVE LOGITS
     lenses
    0.93
     contacts
    0.86
    ioned
    0.85
    kson
    0.82
     tracing
    0.77
    imei
    0.76
     dermat
    0.76
     contact
    0.75
     lens
    0.75
    able
    0.74
    Act Density 0.036%

    No Known Activations