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

    Neuronpedia

    INDEX
    Explanations

    terms related to substitutions or alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raq
    -0.85
    Bird
    -0.73
    arching
    -0.68
    Ł
    -0.67
    naire
    -0.67
    iland
    -0.66
    jah
    -0.65
    slaught
    -0.65
    emi
    -0.64
    è¯
    -0.64
    POSITIVE LOGITS
    itute
    0.95
    utions
    0.94
    aneous
    0.84
     substitutes
    0.77
     substitute
    0.77
    atives
    0.75
     substit
    0.72
    utical
    0.72
     Subst
    0.71
    uting
    0.71
    Act Density 0.007%

    No Known Activations