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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "will" and its variations, indicating future actions or possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cka
    -0.15
    ETY
    -0.15
    allas
    -0.14
    /rfc
    -0.14
    rvé
    -0.14
    -CP
    -0.14
    unas
    -0.14
    .Ribbon
    -0.13
    æĻ¶
    -0.13
    igli
    -0.13
    POSITIVE LOGITS
    oth
    0.18
    isch
    0.16
    ç¤
    0.15
    602
    0.15
    lamaz
    0.15
    ÑĢа
    0.14
    bsp
    0.14
     Panthers
    0.14
    oles
    0.14
    iam
    0.14
    Act Density 0.120%

    No Known Activations