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

    Neuronpedia

    INDEX
    Explanations

    kinds of references to podcasts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esco
    -0.15
    yg
    -0.15
    redient
    -0.15
    ystone
    -0.15
    ibold
    -0.15
    ensitive
    -0.15
    ELY
    -0.14
    oire
    -0.14
    cles
    -0.14
    MBER
    -0.14
    POSITIVE LOGITS
    casts
    0.26
    cast
    0.24
    unk
    0.23
     cast
    0.23
    CAST
    0.23
    iatric
    0.22
    iat
    0.22
    uct
    0.22
    .Pod
    0.21
    yssey
    0.21
    Act Density 0.008%

    No Known Activations