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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to influence and authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     exatamente
    -0.44
    arithmetic
    -0.40
     abnorm
    -0.39
    __":
    -0.38
     exactement
    -0.37
     gynhyrchwyd
    -0.37
    Dichlorobenzene
    -0.35
    flashdata
    -0.35
     دیکھیے
    -0.35
    Genau
    -0.35
    POSITIVE LOGITS
     influence
    1.95
     Influence
    1.88
    influence
    1.84
    Influence
    1.80
     INFLUENCE
    1.72
     influences
    1.67
     Influences
    1.58
     influencia
    1.51
     influencing
    1.50
     Influ
    1.49
    Act Density 0.172%

    No Known Activations