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

    Neuronpedia

    INDEX
    Explanations

    references to various influencing factors in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.56
     latest
    -0.54
     newest
    -0.53
     new
    -0.51
    with
    -0.49
     Aless
    -0.48
    ras
    -0.47
     S
    -0.47
     with
    -0.47
    new
    -0.46
    POSITIVE LOGITS
     factors
    1.54
     Factors
    1.38
    Factors
    1.32
    factors
    1.31
     factores
    1.15
     FACTORS
    1.11
     Faktoren
    1.06
     fatores
    1.04
     fattori
    1.04
     facteurs
    1.03
    Act Density 0.496%

    No Known Activations