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

    Neuronpedia

    INDEX
    Explanations

    phrases related to progression or taking steps forward

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obia
    -0.15
    afone
    -0.15
    quist
    -0.15
    .cg
    -0.15
    ossal
    -0.15
    shed
    -0.14
    rox
    -0.14
    cade
    -0.14
    indir
    -0.14
    isting
    -0.14
    POSITIVE LOGITS
    anca
    0.17
    scribe
    0.17
    809
    0.16
     grips
    0.16
    309
    0.15
    вÑĥ
    0.15
    adal
    0.15
     expl
    0.14
     Gri
    0.14
    anco
    0.14
    Act Density 0.163%

    No Known Activations