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

    Neuronpedia

    INDEX
    Explanations

    the word "following."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -0.52
     ſind
    -0.52
    XtraEditors
    -0.51
    ArgsConstructor
    -0.48
     ſtand
    -0.47
    riwal
    -0.47
     ſer
    -0.46
     cliquer
    -0.46
    Organisateur
    -0.46
     ſch
    -0.46
    POSITIVE LOGITS
     following
    1.30
    following
    0.99
    Following
    0.86
     Following
    0.84
     FOLLOWING
    0.81
     folgende
    0.77
     folgenden
    0.75
     seguinte
    0.73
     seguente
    0.69
    以下
    0.69
    Act Density 0.157%

    No Known Activations