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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases and expressions indicating similarity or likeness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bezeichneter
    -0.84
     Anſ
    -0.82
    Tikang
    -0.79
     Efq
    -0.78
     RSSSF
    -0.78
     myſelf
    -0.76
     Haydn
    -0.75
     gundam
    -0.75
     Majefty
    -0.73
     ―――――
    -0.73
    POSITIVE LOGITS
     the
    0.73
     Like
    0.65
     like
    0.63
     those
    0.63
     a
    0.57
     but
    0.54
    OrEqualTo
    0.53
     called
    0.51
     כמו
    0.51
    like
    0.51
    Act Density 0.345%

    No Known Activations