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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing gratitude or appreciation towards someone

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     avoient
    -0.77
     auroit
    -0.72
    enterOuterAlt
    -0.72
     ainfi
    -0.71
     enfans
    -0.71
     fidélité
    -0.68
     protoimpl
    -0.64
     așa
    -0.63
     decoradas
    -0.63
     feroit
    -0.63
    POSITIVE LOGITS
    plenty
    0.55
     sī
    0.55
    Plenty
    0.53
     ax
    0.53
     plenty
    0.51
    eros
    0.50
     plentiful
    0.50
    Sod
    0.50
    estacks
    0.48
     Follows
    0.48
    Act Density 0.079%

    No Known Activations