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

    Neuronpedia

    INDEX
    Explanations

    descriptors that imply courage, assertiveness, or a strong stance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÏĦαν
    -0.16
    iten
    -0.15
    rete
    -0.15
    orro
    -0.14
    acro
    -0.14
     torture
    -0.14
    iggs
    -0.14
    иÑĤелÑĮно
    -0.14
    ctor
    -0.14
    dup
    -0.14
    POSITIVE LOGITS
    ness
    0.33
    face
    0.26
    -faced
    0.24
    ly
    0.22
     enough
    0.21
    speaker
    0.21
     statement
    0.21
    -face
    0.21
     statements
    0.21
     faced
    0.19
    Act Density 0.028%

    No Known Activations