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

    Neuronpedia

    INDEX
    Explanations

    phrases that reference upward movement or improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inkel
    -0.20
    place
    -0.17
    ع
    -0.16
    quip
    -0.16
    ãĥ¬ãĥĥãĥĪ
    -0.15
    coni
    -0.15
    estr
    -0.15
    odore
    -0.15
    esters
    -0.15
    undler
    -0.15
    POSITIVE LOGITS
    /down
    0.21
    vsp
    0.16
    sk
    0.16
    datable
    0.16
    .gf
    0.16
    dater
    0.15
    ois
    0.15
    eview
    0.14
    gang
    0.14
    744
    0.14
    Act Density 0.080%

    No Known Activations