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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases that highlight differences or contrasts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Filmografie
    -0.57
    хов
    -0.56
    jardin
    -0.54
     evtl
    -0.53
     hereby
    -0.53
    Lester
    -0.52
     Isk
    -0.52
    X
    -0.52
     peck
    -0.52
     Lester
    -0.52
    POSITIVE LOGITS
     unlike
    1.55
    unlike
    1.52
     Unlike
    1.42
    Unlike
    1.40
    lihood
    1.05
    DockStyle
    0.98
     Gegensatz
    0.89
     contrary
    0.88
    Contrary
    0.86
     diferencia
    0.83
    Act Density 0.085%

    No Known Activations