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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "hit" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hire
    -0.19
    ered
    -0.19
    iac
    -0.17
    erre
    -0.16
    erge
    -0.16
    ths
    -0.15
    erie
    -0.15
    eren
    -0.15
    hand
    -0.15
    sed
    -0.15
    POSITIVE LOGITS
    TING
    0.30
    ting
    0.28
    achi
    0.24
    ACHI
    0.21
     parade
    0.19
    ler
    0.19
    REC
    0.18
    maker
    0.17
    /goto
    0.17
    lers
    0.17
    Act Density 0.020%

    No Known Activations