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

    Neuronpedia

    INDEX
    Explanations

    words or phrases denoting proximity or similarity

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to proximity or closeness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ICAN
    -0.77
    AIN
    -0.71
    STE
    -0.63
    dor
    -0.61
    hal
    -0.60
    NZ
    -0.59
    NT
    -0.59
    ilts
    -0.59
    DoS
    -0.55
    oat
    -0.55
    POSITIVE LOGITS
     thereto
    1.02
     enough
    0.98
     to
    0.87
     proximity
    0.84
    enough
    0.83
    sighted
    0.82
     confines
    0.76
    iths
    0.74
     quarters
    0.72
    paren
    0.71
    Act Density 0.025%

    No Known Activations