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

    Neuronpedia

    INDEX
    Explanations

    instances of physical or situational consequences and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agg
    -0.17
    cps
    -0.17
    cent
    -0.15
    ottes
    -0.15
    AME
    -0.14
    onte
    -0.14
     cent
    -0.14
    idth
    -0.14
    irma
    -0.14
    istrov
    -0.14
    POSITIVE LOGITS
    ieg
    0.17
    anka
    0.17
    .sparse
    0.16
    iesel
    0.14
    ãģ²
    0.14
    imm
    0.14
    над
    0.14
     Starr
    0.14
    stdarg
    0.14
     imm
    0.13
    Act Density 0.032%

    No Known Activations