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

    Neuronpedia

    INDEX
    Explanations

    expressions related to similarity and equivalence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     škole
    -0.53
    즘
    -0.51
    agh
    -0.51
    ריך
    -0.48
     Mexicana
    -0.46
    ొ
    -0.45
    ABETH
    -0.45
    DebuggerNonUser
    -0.45
    디오
    -0.45
    umus
    -0.44
    POSITIVE LOGITS
     identical
    2.22
    identical
    1.96
     parallel
    1.71
     Iden
    1.70
     similar
    1.68
     identically
    1.66
     comparable
    1.63
    similar
    1.62
     similarities
    1.61
     similarity
    1.59
    Act Density 0.250%

    No Known Activations