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

    Neuronpedia

    INDEX
    Explanations

    references to "hook" and similar related terms

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     poffible
    -0.98
    Personensuche
    -0.94
     Majefty
    -0.92
     ftate
    -0.81
     ―――――
    -0.81
    Sidenav
    -0.81
     Sien
    -0.81
    ︎
    -0.79
     Asheville
    -0.79
    Filmographie
    -0.78
    POSITIVE LOGITS
     HOOK
    1.76
     hooks
    1.73
     Hooks
    1.69
     Hook
    1.68
    Hook
    1.63
    HOOK
    1.62
     hook
    1.59
    hooks
    1.55
    hook
    1.52
    Hooks
    1.49
    Act Density 0.011%

    No Known Activations