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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate purpose or intent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .habbo
    -0.15
    WSC
    -0.15
    uses
    -0.15
    pp
    -0.15
    WithEmail
    -0.14
    amon
    -0.14
    rello
    -0.14
    kill
    -0.14
    udeau
    -0.14
    ivol
    -0.14
    POSITIVE LOGITS
    -called
    0.36
    oner
    0.26
    iled
    0.26
    oth
    0.25
    ley
    0.25
    aks
    0.24
    ìį¨
    0.23
    iling
    0.23
    apy
    0.23
     they
    0.22
    Act Density 0.038%

    No Known Activations